Recurrent neural networks (RNNs) with dimensionality reduction and break down in computational mechanics; application to multi-scale localization step

DOI10.1016/j.cma.2021.114476OpenAlexW4205691894MaRDI QIDQ2072735

Ludovic Noels, Ling Wu

Publication date: 26 January 2022

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2112.12842

zbMATH Keywords

high dimensionalityrecurrent neural networksdimensionality reductionmulti-scalehistory-dependencelocalization step

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Numerical methods for partial differential equations, boundary value problems (65N99)

Related Items

A micromechanics‐based recurrent neural networks model for path‐dependent cyclic deformation of short fiber composites, Thermodynamically consistent machine-learned internal state variable approach for data-driven modeling of path-dependent materials, Transfer learning of recurrent neural network‐based plasticity models, Neural integration for constitutive equations using small data, A UMAP-based clustering method for multi-scale damage analysis of laminates

Uses Software

• darch
• F3DAM

Cites Work

• Unnamed Item
• Accurate cyclic plastic analysis using a neural network material model
• The reduced model multiscale method (R3M) for the nonlinear homogenization of hyperelastic media at finite strains
• Artificial neural network as an incremental nonlinear constitutive model for a finite element code.
• Simulation of the multi-scale convergence in computational homogenization approaches
• Principal component analysis.
• Effective properties of composite materials with periodic microstructure: A computational approach
• Meta-modeling game for deriving theory-consistent, microstructure-based traction-separation laws via deep reinforcement learning
• Smart constitutive laws: inelastic homogenization through machine learning
• Bayesian inference of non-linear multiscale model parameters accelerated by a deep neural network
• Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network
• An intelligent nonlinear meta element for elastoplastic continua: deep learning using a new time-distributed residual U-net architecture
• Micromechanics-based surrogate models for the response of composites: a critical comparison between a classical mesoscale constitutive model, hyper-reduction and neural networks
• A recurrent neural network-accelerated multi-scale model for elasto-plastic heterogeneous materials subjected to random cyclic and non-proportional loading paths
• Micromechanics-based material networks revisited from the interaction viewpoint; robust and efficient implementation for multi-phase composites
• A framework for data-driven analysis of materials under uncertainty: countering the curse of dimensionality
• Unified treatment of microscopic boundary conditions and efficient algorithms for estimating tangent operators of the homogenized behavior in the computational homogenization method
• Computational homogenization of heterogeneous materials with finite elements
• Characterizing rate-dependent material behaviors in self-learning simulation
• Computational homogenization of nonlinear elastic materials using neural networks
• Reducing the Dimensionality of Data with Neural Networks
• Numerical implementation of a neural network based material model in finite element analysis
• An approach to micro-macro modeling of heterogeneous materials